arXiv research

Develops a new model for RLHF accounting for partially observed states and intermediate feedback.

Paper solves tracking control for $(x,u)$-flat systems using classical states.

Feedback improves ESN performance by 30-60% across various tasks.

Study of reinforcement learning with additional feedback observations.

Enhanced feedback model improves sample-efficiency in POMDPs.

Reinforcement learning with trajectory feedback instead of state-action rewards.

Safe RL with binary feedback using SABRE algorithm.

Algorithm improves query recommendations with immediate user feedback.

Efficient boosting method for regression with limited feedback.

Recommenders personalize the web content by typically using collaborative filtering to relate users (or items) based on explicit feedback, e.g., ratings. The difficulty of collecting this feedback has recently motivated to consider implicit feedback (e.g., item consumption along with the corresponding time). In this pa…

Learning from human feedback is a viable alternative to control design that does not require modelling or control expertise. Particularly, learning from corrective advice garners advantages over evaluative feedback as it is a more intuitive and scalable format. The current state-of-the-art in this field, COACH, has pro…

GAIF enhances online multiple testing with feedback, improving statistical power.

DOPL learns from preference feedback to solve RMAB problems.

The problem of Reinforcement Learning (RL) in an unknown nonlinear dynamical system is equivalent to the search for an optimal feedback law utilizing the simulations/ rollouts of the dynamical system. Most RL techniques search over a complex global nonlinear feedback parametrization making them suffer from high trainin…

This work compares human feedback methods for reward learning in bandits.

Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models. However, autoregressive feedback exposes the evolution of the hidden state trajectory to potential biases from well-known train-test discrepancies.…

New Q-learning algorithms reduce regret in inventory control problems.

Reduces user feedback needed for accurate recommender systems.

Neural ODEs control graph dynamics with low energy feedback.

A new method shapes reinforcement learning environments by abstracting large state spaces.

Study uses geometric algebra to analyze credit cycles, revealing dangerous feedback loops.

We study an online decision making problem where on each round a learner chooses a list of items based on some side information, receives a scalar feedback value for each individual item, and a reward that is linearly related to this feedback. These problems, known as contextual semibandits, arise in crowdsourcing, rec…

We propose a novel {\it Equilibrated Recurrent Neural Network} (ERNN) to combat the issues of inaccuracy and instability in conventional RNNs. Drawing upon the concept of autapse in neuroscience, we propose augmenting an RNN with a time-delayed self-feedback loop. Our sole purpose is to modify the dynamics of each inte…

Imitation learning is a control design paradigm that seeks to learn a control policy reproducing demonstrations from expert agents. By substituting expert demonstrations for optimal behaviours, the same paradigm leads to the design of control policies closely approximating the optimal state-feedback. This approach requ…

Perfect tracking control for real-world Euler-Lagrange systems is challenging due to uncertainties in the system model and external disturbances. The magnitude of the tracking error can be reduced either by increasing the feedback gains or improving the model of the system. The latter is clearly preferable as it allows…

Algorithm learns actions from past states in complex tasks.

Paper introduces a new framework for optimizing non-convex functions.

Study controlled contagion with state-dependent killing, proving a comparison principle.

In this paper we consider $(x,u)$-flat nonlinear control systems with two inputs, and show that every such system can be rendered static feedback linearizable by prolongations of a suitably chosen control. This result is not only of theoretical interest, but has also important implications on the design of flatness bas…

New method provides fine-grained feedback on interactive student programs.

Improved GRU model with weighted time-delay feedback for long-term dependencies.

CNN-F uses generative feedback to improve neural networks' robustness to perturbations.

Paper models and compresses wideband CSI feedback in FDD MIMO systems.

Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the machine to adapt to the users' intentions and preferences. Often, this takes the…

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to better utilize the available spatial diversity and multiplexing gains. However, in a frequency division duplex (FDD) massive MIMO system, CSI feedback overhead degrades the overall spectral…

LLM trading agents show risk feedback can improve alignment without fine-tuning.

Study preference-based reinforcement learning in episodic kernel MDPs.

Framework learns robust control policies from expert demonstrations.

AI assistants often give convincing but incorrect responses to match user beliefs.

The paper is devoted to the local classification of generic control-affine systems on an n-dimensional manifold with scalar input for any n>3 or with two inputs for n=4 and n=5, up to state-feedback transformations, preserving the affine structure. First using the Poincare series of moduli numbers we introduce the intr…

We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets). This model is incorporated with a robust class of spectral graph filters, called feedback-looped filters, to provide better localization on vertices, while still attaining…

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

Hölder-DPO aligns models robustly with noisy human feedback.

Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We propose using oracle feedback to learn a predictive model of these blind spots to red…

New algorithm reduces reinforcement learning regret for linear MDPs with unknown transitions.

Conventional collaborative filtering techniques treat a top-n recommendations problem as a task of generating a list of the most relevant items. This formulation, however, disregards an opposite - avoiding recommendations with completely irrelevant items. Due to that bias, standard algorithms, as well as commonly used …

Paper presents a novel framework for OOD learning with human feedback.

Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an optimal trajectory fr…